Key result
Recurrent neural networks using attention and MFCC features achieve state-of-the-art PCG segmentation over classical methods.
Why the study?
Heart sound segmentation is a crucial pre-processing step for many diagnostic applications, and existing methods are less accurate or labor intensive.
A novel bidirectional LSTM with attention using MFCC features provides highly accurate, automated segmentation of heart sounds, potentially improving downstream diagnostic applications like murmur detection.
May aid automated phonocardiogram research pipelines; leaves open prospective clinical validation before diagnostic use.
OBJECTIVE: This paper proposes a novel framework for the segmentation of phonocardiogram (PCG) signals into heart states, exploiting the temporal evolution of the PCG as well as considering the salient information that it provides for the detection of the heart state. METHODS: We propose the use of recurrent neural networks and exploit recent advancements in attention based learning to segment the PCG signal. This allows the network to identify the most salient aspects of the signal and disregard uninformative information. RESULTS: The proposed method attains state-of-the-art performance on multiple benchmarks including both human and animal heart recordings. Furthermore, we empirically analyse different feature combinations including envelop features, wavelet and Mel Frequency Cepstral Coefficients (MFCC), and provide quantitative measurements that explore the importance of different features in the proposed approach. CONCLUSION: We demonstrate that a recurrent neural network coupled with attention mechanisms can effectively learn from irregular and noisy PCG recordings. Our analysis of different feature combinations shows that MFCC features and their derivatives offer the best performance compared to classical wavelet and envelop features. SIGNIFICANCE: Heart sound segmentation is a crucial pre-processing step for many diagnostic applications. The proposed method provides a cost effective alternative to labour extensive manual segmentation, and provides a more accurate segmentation than existing methods. As such, it can improve the performance of further analysis including the detection of murmurs and ejection clicks. The proposed method is also applicable for detection and segmentation of other one dimensional biomedical signals.
No takes yet. Share an insight, caveat, or question.
A 2019 study studied Heart sound segmentation. Bidirectional LSTMs with Attention and MFCC features vs. Classical wavelet and envelop features / existing methods was evaluated on Segmentation of phonocardiogram (PCG) signals into heart states. A recurrent neural network coupled with attention mechanisms using MFCC features attained state-of-the-art performance for segmenting phonocardiogram signals compared to classical features.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: